{"id":"W3214379748","doi":"","title":"Are My Deep Learning Systems Fair? An Empirical Study of Fixed-Seed Training","year":2021,"lang":"en","type":"article","venue":"Neural Information Processing Systems","topic":"Ethics and Social Impacts of AI","field":"Social Sciences","cited_by":20,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Training (meteorology); Computer science; Artificial intelligence; Machine learning; Geography","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["sts","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.001762167,0.0001560664,0.0004050056,0.0001298833,0.001355163,0.001601345,0.0002508783,0.0002379437,0.000006777368],"category_scores_gemma":[0.001570661,0.0001508279,0.00005801417,0.000641534,0.000120414,0.004362214,0.00004069202,0.0004635599,0.000008002753],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001132976,"about_ca_system_score_gemma":0.0003879952,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001520891,"about_ca_topic_score_gemma":0.0006683004,"domain_scores_codex":[0.9968337,0.00079273,0.000827912,0.0001717811,0.001002401,0.0003714438],"domain_scores_gemma":[0.9968427,0.0001575132,0.001075832,0.0001482485,0.001574844,0.0002008746],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"qualitative","study_design_gemma":"qualitative","study_design_scores_codex":[0.00002116149,0.0001814576,0.04022121,0.0006500392,0.00003961976,0.00001346149,0.9214987,0.02649861,0.00006704327,0.001526014,0.00008791021,0.009194748],"study_design_scores_gemma":[0.000454329,0.0001593837,0.008389547,0.0002284537,0.00002339752,0.000007688347,0.9429666,0.04346897,0.000007099716,0.00004143728,0.00403865,0.0002144527],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9886097,0.0003057866,0.0005978748,0.0005136672,0.0009094151,0.0004679968,0.000003753532,0.0002222022,0.008369637],"genre_scores_gemma":[0.9991314,0.000008438706,0.00002018272,0.0001864572,0.000312696,0.00002543041,0.00001713434,0.00001271332,0.0002855522],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.03183166,"threshold_uncertainty_score":0.9999449,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1161021505810194,"score_gpt":0.4009260998072039,"score_spread":0.2848239492261845,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}